Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2059 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4701. Min Act: -0.0000

Data Index: 376806 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1738404 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3911. Min Act: -0.0000

Data Index: 907142 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1281501 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1131168 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3745. Min Act: -0.0000

Data Index: 369880 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1282205 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1784760 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3568. Min Act: -0.0000

Data Index: 840614 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3296. Min Act: -0.0000

Data Index: 928032 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3430. Min Act: -0.0000

Data Index: 455087 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3213. Min Act: -0.0000

Data Index: 307491 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1469881 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1996649 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1188396 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3149. Min Act: -0.0000

Data Index: 748975 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1510745 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3068. Min Act: -0.0000

Data Index: 216671 (The Pile)

Max Activating Token Index: 141

Text #18

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1996450 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1241045 (The Pile)

Max Activating Token Index: 278